© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58259
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ቭ
    -2.06
    During
    -2.06
     zweiten
    -2.05
    就是
    -1.91
    3
    -1.91
     ので
    -1.91
    所有的
    -1.91
    From
    -1.88
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.86
    You
    -1.86
    POSITIVE LOGITS
     of
    2.17
    ſſen
    2.13
    
    2.08
    @~
    2.08
    medriver
    2.06
    亖
    2.05
    狨
    2.03
    だけではなく
    1.97
    jh
    1.91
     majú
    1.86
    Activations Density 0.005%

    No Known Activations